Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Pudding, budding, Prisma, PTA, DEX

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.51
    ен
    1.50
    ная
    1.44
    ное
    1.41
    ные
    1.40
     量
    1.34
    রা
    1.34
    ы
    1.33
    ный
    1.30
    ).
    1.29
    POSITIVE LOGITS
    a
    2.14
    o
    1.88
    e
    1.84
    er
    1.84
    ה
    1.80
    eight
    1.72
    ו
    1.66
    oğlu
    1.62
    oC
    1.60
    珑
    1.55
    Act Density 0.003%

    No Known Activations